Update calendar_rag.py

calendar_rag.py

@@ -447,7 +447,35 @@ class PipelineConfig:
     localization: LocalizationConfig = field(default_factory=LocalizationConfig)
 
 def create_default_config(api_key: str) -> PipelineConfig:
-    return PipelineConfig(model=ModelConfig(openai_api_key=api_key))
+    """
+    Create a default pipeline configuration with optimized settings for Thai language processing.
+    
+    Args:
+        api_key (str): OpenAI API key
+        
+    Returns:
+        PipelineConfig: Configured pipeline settings
+    """
+    return PipelineConfig(
+        model=ModelConfig(
+            openai_api_key=api_key,
+            temperature=0.3  # Lower temperature for more focused responses
+        ),
+        retriever=RetrieverConfig(
+            top_k=5  # Optimal number of documents to retrieve
+        ),
+        cache=CacheConfig(
+            enabled=True,
+            cache_dir=Path("./cache"),
+            ttl=86400  # 24 hour cache
+        ),
+        processing=ProcessingConfig(
+            batch_size=32  # Default batch size for processing
+        ),
+        localization=LocalizationConfig(
+            enable_thai_normalization=True  # Enable Thai text normalization
+        )
+    )
 
 class CalendarDataProcessor:
     """Process and structure calendar data from the new raw-data.json format"""
@@ -1384,7 +1412,7 @@ class AcademicCalendarRAG:
                 event_type=query_info.get("event_type"),
                 semester=query_info.get("semester"),
                 top_k=self.config.retriever.top_k,
-                weight_semantic=weight_semantic
+                weight_semantic= 0.3
             )
             
             # Add fee information for fee-related queries
@@ -1422,10 +1450,6 @@ class AcademicCalendarRAG:
         
 #         # Create config with hybrid retrieval settings
 #         config = create_default_config(openai_api_key)
-#         config.localization.enable_thai_normalization = True
-#         config.retriever.top_k = 5
-#         config.model.temperature = 0.3
-        
 #         pipeline = AcademicCalendarRAG(config)
         
 #         # Load and process data
@@ -1435,13 +1459,13 @@ class AcademicCalendarRAG:
 #         pipeline.load_data(raw_data)
         
 #         # Test queries with different semantic weights
-#         queries = ["เปิดเทอมวันเเรกวันไหน"]
+#         queries = ["มีวิชาหลักหรือวิชาเลือกอะไรบ้าง"]
         
 #         print("=" * 80)
         
 #         for query in queries:
 #             print(f"\nQuery: {query}")
-#             result = pipeline.process_query(query, weight_semantic=0.3)
+#             result = pipeline.process_query(query)
 #             print(f"Answer: {result['answer']}")
 #             print("-" * 40)